{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LSNUWX73DRYFBE2O2KJWWIMCSI","short_pith_number":"pith:LSNUWX73","schema_version":"1.0","canonical_sha256":"5c9b4b5ffb1c7050934ed2936b21829227d25fe8394a22108ff81e1861f1754c","source":{"kind":"arxiv","id":"2106.08873","version":1},"attestation_state":"computed","paper":{"title":"Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alejandro Mottini, Jaime Lorenzo-Trueba, Sri Vishnu Kumar Karlapati, Thomas Drugman","submitted_at":"2021-06-16T15:47:06Z","abstract_excerpt":"Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a rich literature on VC, most proposed methods are trained and evaluated on clean speech recordings. However, many acoustic environments are noisy and reverberant, severely restricting the applicability of popular VC methods to such scenarios. To address this limitation, we propose Voicy, a new VC framework particularly tailored for noisy speech. Our method, which is inspired by the de-noising auto-encoders framework, i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.08873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-16T15:47:06Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c6663ea2736dacde5bc46d2c50a5e1365e05b66f1f16e6979973017c1fdfade7","abstract_canon_sha256":"1516e8d4cfb60b266cf7dfc31467346343e8061a27fcbbdb97af504325ed4b51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:02.198941Z","signature_b64":"ieDrplPBYlelaTH36/bOyZMQsGw7+k7fYrLfIPAoNdQuZWV4+X3ox2bu6subAO9ZKgbszv+2eo8ZSN2lTmzEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c9b4b5ffb1c7050934ed2936b21829227d25fe8394a22108ff81e1861f1754c","last_reissued_at":"2026-07-05T02:50:02.198590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:02.198590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alejandro Mottini, Jaime Lorenzo-Trueba, Sri Vishnu Kumar Karlapati, Thomas Drugman","submitted_at":"2021-06-16T15:47:06Z","abstract_excerpt":"Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a rich literature on VC, most proposed methods are trained and evaluated on clean speech recordings. However, many acoustic environments are noisy and reverberant, severely restricting the applicability of popular VC methods to such scenarios. To address this limitation, we propose Voicy, a new VC framework particularly tailored for noisy speech. Our method, which is inspired by the de-noising auto-encoders framework, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08873","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.08873/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.08873","created_at":"2026-07-05T02:50:02.198653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08873v1","created_at":"2026-07-05T02:50:02.198653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08873","created_at":"2026-07-05T02:50:02.198653+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSNUWX73DRYF","created_at":"2026-07-05T02:50:02.198653+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSNUWX73DRYFBE2O","created_at":"2026-07-05T02:50:02.198653+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSNUWX73","created_at":"2026-07-05T02:50:02.198653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI","json":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI.json","graph_json":"https://pith.science/api/pith-number/LSNUWX73DRYFBE2O2KJWWIMCSI/graph.json","events_json":"https://pith.science/api/pith-number/LSNUWX73DRYFBE2O2KJWWIMCSI/events.json","paper":"https://pith.science/paper/LSNUWX73"},"agent_actions":{"view_html":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI","download_json":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI.json","view_paper":"https://pith.science/paper/LSNUWX73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08873&json=true","fetch_graph":"https://pith.science/api/pith-number/LSNUWX73DRYFBE2O2KJWWIMCSI/graph.json","fetch_events":"https://pith.science/api/pith-number/LSNUWX73DRYFBE2O2KJWWIMCSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI/action/storage_attestation","attest_author":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI/action/author_attestation","sign_citation":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI/action/citation_signature","submit_replication":"https://pith.science/pith/LSNUWX73DRYFBE2O2KJWWIMCSI/action/replication_record"}},"created_at":"2026-07-05T02:50:02.198653+00:00","updated_at":"2026-07-05T02:50:02.198653+00:00"}